AgentComparison
Lindy · product · AI teammate in Slack

Lindy

An AI teammate in Slack with integration write guardrails whose scope depends on channel and settings.

Group: Work and business agents

Lindy describes an AI teammate that lives in Slack and knows what your company knows. Everyone gets a private Lindy in DMs and a shared one in channels. Its docs list answering questions across tools, multi-step actions and creating decks, sheets and reports.

Documentation researched, not testedChecked 23 October 2026Vendor documentation, not a test

The decision in plain English

Current pricing starts at $49.99 per active user per month for 5,000 credits, with top-ups at $10 per 1,000. The pricing FAQ says outside-impact actions always wait for approval, but the integration documentation limits write guardrails to shared Slack threads and allows Always allow. Do not assume every channel or account has a human approval gate.

Best fit

Teams using shared Slack threads who can configure integration write guardrails and review which account each connection represents.

Poor fit

Solo users who do not use Slack, or teams that need a free plan beyond the 7-day trial credits.

Documented capabilities

Vendor statements, not verified task outcomes.

  • Slack teammate with private DMs and shared channel use Source · checked 2026-10-14
  • Configurable write guardrails in shared Slack threads Source · checked 2026-10-14

Permissions and human control

  • Integration docs list Always allow (writes without asking), Require approval (asks in Slack) and Don't offer (no writes with the tool). Reads are not guarded. These write guardrails apply only in shared Slack threads, not web chat, Slack DMs, iMessage or SMS.
  • The pricing FAQ still says outside-impact actions wait for approval. That conflicts with the narrower channel/settings scope in the integration docs; verify the actual configuration before relying on approval.

Documented controls do not prove that an agent always follows them.

Limits and open questions

  • Free credits last 7 days; paid usage starts at $49.99 per user per month for 5,000 credits.
  • Every active workspace user is billed a seat
  • Monthly credits do not roll over
  • Described by the vendor; not tested by AgentComparison
  • Write guardrails cover shared Slack threads, not web chat, Slack DMs, iMessage or SMS, per integration docs.
  • The pricing FAQ makes a broader approval claim than the integration docs. A guardrail applies across all accounts of an integration, not separately per account.

Privacy and security

The privacy notice, dated 28 September 2026, lists cloud, AI, integration and communication providers. It excludes Google API data from AI model training or evaluation and says personal information will not train a generative AI product. It retains data as needed for the stated purposes and legal requirements, with deletion or anonymization when no longer needed; backups may be isolated until deletion is possible. It does not give a single fixed deletion deadline. These are policy statements, not an independent security audit.

Feature-by-feature: what is documented and what is not

Official sources checked 23 October 2026. A documented feature is a vendor statement, not proof of success.

FeatureEvidence statusDetail and limit
Shared and private workDocumentedChannel mentions continue inside the thread. DMs have the fuller private toolset; shared-channel answers have narrower public-safe scope. Source
Personal and team connectionsIdentity mattersOwners/admins can share a connection. Everyone then acts with that connected account's permissions, not necessarily their own. Source
Write guardrailsShared Slack threads onlyAlways allow, Require approval and Don't offer govern writes. Web chat, Slack DMs, iMessage and SMS are outside these guardrails. Source
Read accessNot guardedReads are not approval-gated by these write guardrails. Connecting a tool enables all its actions; inspect the actual account scope. Source
Who can approveDocumentedRequester or workspace owner/admin can approve an action. Always allow changes future behavior, with scope depending on who chooses it. Source
Pricing and seatsPublished, not a usage forecastFrom $29.99 per active user/month for 3,000 credits each, pooled (cut from $49.99/5,000 before 23 Oct 2026). Top-ups $10/1,000; monthly credits do not roll over; Lindy pauses credit-using actions at the cap. Source
Approval claim conflictUnresolved in vendor pagesPricing FAQ says all outside-impact actions await approval, while integration docs limit guardrails by channel and allow silent writes. Do not rely on the broad FAQ alone. Source
Privacy and retentionPolicy, not testedPolicy excludes Google API training/evaluation and gives purpose/legal retention criteria, not a universal deletion deadline. Source

How to start with Lindy narrowly

  1. Review active-seat billing and the seven-day trial limit before inviting or mentioning teammates.
  2. Connect only the account needed for a small task. Keep it personal unless you intend the team to use that account's permissions.
  3. If using shared Slack threads, choose Require approval or Don't offer for relevant integrations, and check who can change the rule.
  4. Do not assume those guardrails apply in DMs, web chat, iMessage or SMS. Start with a read-only task and check the actual source and account.
  5. Review recorded actions, credit use and connection health before increasing scope; disconnect unused connections.

Official product/setup source. These are documentation-based steps, not a hands-on setup test.

Common questions about Lindy

What is Lindy for?

Teams using shared Slack threads who can configure integration write guardrails and review which account each connection represents. The vendor describes it as: Lindy describes an AI teammate that lives in Slack and knows what your company knows. Everyone gets a private Lindy in DMs and a shared one in channels. Its docs list answering questions across tools, multi-step actions and creating decks, sheets and reports.

Who should look elsewhere?

Solo users who do not use Slack, or teams that need a free plan beyond the 7-day trial credits.

How much does Lindy cost?

Pricing page re-verified 23 October 2026: Team is now from $29.99 per active user/month for 3,000 credits each (previously $49.99/5,000 - cut between 22 and 23 October). Free tier: $50 in credits lasting 7 days, no card. Top-ups remain $10 per 1,000 credits, pooled workspace; credits do not roll over; Lindy pauses credit-using actions at the cap rather than surprise-billing. Slack joiners get a 7-day free trial before the seat is billed; direct signups are billed immediately.

What can it access and what needs my approval?

Integration docs list Always allow (writes without asking), Require approval (asks in Slack) and Don't offer (no writes with the tool). Reads are not guarded. These write guardrails apply only in shared Slack threads, not web chat, Slack DMs, iMessage or SMS. The pricing FAQ still says outside-impact actions wait for approval. That conflicts with the narrower channel/settings scope in the integration docs; verify the actual configuration before relying on approval.

What happens to my data?

The privacy notice, dated 28 September 2026, lists cloud, AI, integration and communication providers. It excludes Google API data from AI model training or evaluation and says personal information will not train a generative AI product. It retains data as needed for the stated purposes and legal requirements, with deletion or anonymization when no longer needed; backups may be isolated until deletion is possible. It does not give a single fixed deletion deadline. These are policy statements, not an independent security audit.

Has AgentComparison tested it?

No. This record is built from the vendor's own documentation, checked 2026-10-23. Vendor claims are attributed, not confirmed.

How to evaluate Lindy yourself

  1. Pick one low-risk task that matches its documented capabilities: slack teammate with private dms and shared channel use.
  2. Write the expected output and what counts as failure before you start.
  3. Connect the minimum access needed, and check approval settings first.
  4. Run it twice and compare, then review every action it took.
  5. Check cost after any free allowance. Unknown price is not free.

Related

Sources and history

Change history

Documentation overview expanded with current pricing/access sources. No hands-on results claimed.

Report a correction